Skip to content

ModelListedExternal

IP Adapter

Project Page | Paper (ArXiv) | Code

Sourcehuggingface.co/h94/IP-Adapter/tree/018e402774aeeddd60609b4ecdb7e298259dc729

KindOtherVersionRevision 018e402

Model source

Kind: Other
File size: 41.6 MB–3.44 GB
Version: vRevision 018e402
Updated: Sep 30, 2026
Downloads: 0
Tasks: Text to image
Source: Hugging Face

Source excerpt

Project Page | Paper (ArXiv) | Code

Related resources

34 connections

Used bySimple LCM img2vid workflow | ComfyUI — v4 Used byComfyUI Image Workflows — V16 Used byComfyUI Image Workflows — V17 Used byComfyUI Image Workflows — V9.0 Used by(Video Tutorial Resources) Flux hyper, SDXL 2 Flux Outpainting + Text FX Bonus — v1.0 Used byComfyUI Image Workflows — V27 Used bySimplified Single Image 2 Video — v1.0 Used byDonutsDelivery SDXL Workflow (Simplified) - Upscale, Facedetailer, Ipadapter — MiniDonut V3 Used byComfyUI Image Workflows — V24 Used byComfyUI Image Workflows — V22 Used byComfyUI Image Workflows — V14 Used byComfyUI Image Workflows — V4.0 Used byComfyUI Image Workflows — V32 Used byComfyUI Image Workflows — V19 Used byComfyUI Image Workflows — V37 Used byComfyUI Image Workflows — V18 Used byDonutsDelivery SDXL Workflow (Simplified) - Upscale, Facedetailer, Ipadapter — MiniDonut v4 Used byComfyUI Image Workflows — V7.0 Used byComfyUI Image Workflows — V28 Used byComfyUI Image Workflows — V6.0 Used byComfyUI Image Workflows — V37 — V38 Used byComfyUI Image Workflows — V20 Used byComfyUI Image Workflows — V33 Used byComfyUI Image Workflows — V29 Used byComfyUI Image Workflows — V34 Used byComfyUI Image Workflows — V37 — V39 Used byComfyUI Image Workflows — V21 Used byComfyUI Image Workflows — V35 Used byComfyUI Image Workflows — V30 Used byComfyUI Image Workflows — V10 Used byDonutsDelivery SDXL Workflow (Simplified) - Upscale, Facedetailer, Ipadapter — MiniDonut v5 Used byComfyUI Image Workflows — V36 Used byComfyUI Image Workflows — V12 Used byComfyUI Image Workflows — V26

Sources

1 source

Hugging FacePrimaryVersion 018e402774aeeddd60609b4ecdb7e298259dc729

huggingface.co/h94/IP-Adapter/tree/018e402774aeeddd60609b4ecdb7e298259dc729

Verified Sep 30

Model artifacts

25 artifacts

models/image_encoder/model.safetensors

safetensors · 2.35 GB · SHA-256 6ca9667da1ca…b030 · Hugging Face

models/image_encoder/pytorch_model.bin

bin · 2.35 GB · SHA-256 3d3ec1e66737…9193 · Hugging Face

models/ip-adapter_sd15_light_v11.bin

bin · 42.6 MB · SHA-256 350b63a57847…972b · Hugging Face

models/ip-adapter_sd15_light.bin

bin · 42.6 MB · SHA-256 f71bfbdd937f…b7e1 · Hugging Face

models/ip-adapter_sd15_light.safetensors

safetensors · 42.6 MB · SHA-256 0747d08db670…bb26 · Hugging Face

models/ip-adapter_sd15_vit-G.bin

bin · 44.1 MB · SHA-256 1398e9ae37cb…c474 · Hugging Face

models/ip-adapter_sd15_vit-G.safetensors

safetensors · 44.1 MB · SHA-256 a26f736af07b…c90b · Hugging Face

models/ip-adapter_sd15.bin

bin · 42.6 MB · SHA-256 68e1df30d760…0058 · Hugging Face

models/ip-adapter_sd15.safetensors

safetensors · 42.6 MB · SHA-256 289b45f16d04…3369 · Hugging Face

models/ip-adapter-full-face_sd15.bin

bin · 41.6 MB · SHA-256 47ec4644114f…d1dc · Hugging Face

models/ip-adapter-full-face_sd15.safetensors

safetensors · 41.6 MB · SHA-256 f4a17fb643bf…c6f3 · Hugging Face

models/ip-adapter-plus_sd15.bin

bin · 151 MB · SHA-256 1cb77fc06133…17ba · Hugging Face

models/ip-adapter-plus_sd15.safetensors

safetensors · 93.6 MB · SHA-256 a1c250be4045…4996 · Hugging Face

models/ip-adapter-plus-face_sd15.bin

bin · 93.6 MB · SHA-256 aa09c22b49ef…e0c9 · Hugging Face

models/ip-adapter-plus-face_sd15.safetensors

safetensors · 93.6 MB · SHA-256 1c9edc21af6f…569b · Hugging Face

sdxl_models/image_encoder/model.safetensors

safetensors · 3.44 GB · SHA-256 657723e09f46…d64d · Hugging Face

sdxl_models/image_encoder/pytorch_model.bin

bin · 3.44 GB · SHA-256 2999562fbc02…2d80 · Hugging Face

sdxl_models/ip-adapter_sdxl_vit-h.bin

bin · 666 MB · SHA-256 6b382e2501d0…5929 · Hugging Face

sdxl_models/ip-adapter_sdxl_vit-h.safetensors

safetensors · 666 MB · SHA-256 ebf05d918348…1831 · Hugging Face

sdxl_models/ip-adapter_sdxl.bin

bin · 670 MB · SHA-256 7525f2731e9e…4c12 · Hugging Face

sdxl_models/ip-adapter_sdxl.safetensors

safetensors · 670 MB · SHA-256 ba1002529e78…ebb6 · Hugging Face

sdxl_models/ip-adapter-plus_sdxl_vit-h.bin

bin · 967 MB · SHA-256 ec70edb7cc8e…de90 · Hugging Face

sdxl_models/ip-adapter-plus_sdxl_vit-h.safetensors

safetensors · 808 MB · SHA-256 3f5062b8400c…6581 · Hugging Face

sdxl_models/ip-adapter-plus-face_sdxl_vit-h.bin

bin · 967 MB · SHA-256 50e886d82940…fc36 · Hugging Face

sdxl_models/ip-adapter-plus-face_sdxl_vit-h.safetensors

safetensors · 808 MB · SHA-256 677ad8860204…92c1 · Hugging Face

Source excerpts

3 excerpts

ReadmeSep 28huggingface.co/h94/IP-Adapter

--- tags: - text-to-image - stable-diffusion license: apache-2.0 language: - en library_name: diffusers --- # IP-Adapter Model Card <div align="center"> [**Project Page**](https://ip-adapter.github.io) **|** [**Paper (ArXiv)**](https://arxiv.org/abs/2308.06721) **|** [**Code**](https://github.com/tencent-ailab/IP-Adapter) </div> --- ## Introduction we present IP-Adapter, an effective and lightweight adapter to achieve image prompt capability for the pre-trained text-to-image diffusion models. An IP-Adapter with only 22M parameters can achieve comparable or even better performance to a fine-tuned image prompt model. IP-Adapter can be generalized not only to other custom models fine-tuned from the same base model, but also to controllable generation using existing controllable tools. Moreover, the image prompt can also work well with the text prompt to accomplish multimodal image generation. ![arch](./fig1.png) ## Models ### Image Encoder - [models/image_encoder](https://huggingface.co/h94/IP-Adapter/tree/main/models/image_encoder): [OpenCLIP-ViT-H-14](https://huggingface.co/laion/CLIP-ViT-H-14-laion2B-s32B-b79K) with 632.08M parameter - [sdxl_models/image_encoder](https://huggingface.co/h94/IP-Adapter/tree/main/sdxl_models/image_encoder): [OpenCLIP-ViT-bigG-14](https://huggingface.co/laion/CLIP-ViT-bigG-14-laion2B-39B-b160k) with 1844.9M parameter More information can be found [here](https://laion.ai/blog/giant-openclip/) ### IP-Adapter for SD 1.5 - [ip-adapter_sd15.bin](https://huggingface.co/h94/IP-Adapter/blob/main/models/ip-adapter_sd15.bin): use global image embedding from OpenCLIP-ViT-H-14 as condition - [ip-adapter_sd15_light.bin](https://huggingface.co/h94/IP-Adapter/blob/main/models/ip-adapter_sd15_light.bin): same as ip-adapter_sd15, but more compatible with text prompt - [ip-adapter-plus_sd15.bin](https://huggingface.co/h94/IP-Adapter/blob/main/models/ip-adapter-plus_sd15.bin): use patch image embeddings from OpenCLIP-ViT-H-14 as condition, closer to the reference image than ip-adapter_sd15 - [ip-adapter-plus-face_sd15.bin](https://huggingface.co/h94/IP-Adapter/blob/main/models/ip-adapter-plus-face_sd15.bin): same as ip-adapter-plus_sd15, but use cropped face image as condition ### IP-Adapter for SDXL 1.0 - [ip-adapter_sdxl.bin](https://huggingface.co/h94/IP-Adapter/blob/main/sdxl_models/ip-adapter_sdxl.bin): use global image embeddi...

NoteSep 30huggingface.co/h94/IP-Adapter

Source context: 0 downloads · 1427 likes · Pipeline text-to-image · Library diffusers · Repo h94/IP-Adapter

NoteSep 28huggingface.co/h94/IP-Adapter

Source context: 0 downloads · 1426 likes · Pipeline text-to-image · Library diffusers · Repo h94/IP-Adapter